Printed Arabic Character Classification Using Cadre of Level Feature Extraction Technique

Feature extraction techniques is important in character recognition, because they can enhance the efficacy of recognition in comparison to other approaches. This study aims to investigate the novel feature extraction technique called the Cadre of Level technique in order to represent printed characters and digits. This technique gives statistic and morphologic information, i.e. the calculation is based on a statistical approach but in the positions which can give some information about the morphologic of character. The image of a character is divided into 100 zones, then for each zone we average 5 extracted values (one value for each level) to 1 value for each zone, which gives 100 features for each character. This technique was applied to 105 different characters and 10 different digits of Arabic printed script. K-Nearest Neighbor algorithm was used to classify the printed characters and digits.

@article{Nouri2013,
  title     = {Printed Arabic Character Classification Using Cadre of Level Feature Extraction Technique},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {3},
  number    = {2},
  year      = {2013},
  publisher = {The Science and Information Organization},
  note      = {Special Issue on Selected Papers from Third international symposium on Automatic Amazigh processing SITACAM13},
  author    = {S. Nouri and M.Fakir},
  doi       = {10.14569/SpecialIssue.2013.030209},
  url       = {https://doi.org/10.14569/SpecialIssue.2013.030209}
}